© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10441
    Prev
    Next
    INDEX
    Explanations

    variations of the word "scratch" in different contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    enterOuterAlt
    -0.98
     Hoyt
    -0.80
     Enid
    -0.75
     Lenz
    -0.75
    PositiveButton
    -0.74
    didSet
    -0.73
    hofen
    -0.71
    IVersion
    -0.71
     pełni
    -0.69
    forName
    -0.69
    POSITIVE LOGITS
     Scratch
    1.70
     scratch
    1.70
    Scratch
    1.55
     scratching
    1.49
    scratch
    1.48
     scratches
    1.41
     SCR
    1.28
     scratched
    1.23
     scrat
    1.17
    SCR
    1.09
    Activations Density 0.006%

    No Known Activations